J. Biomedical Science and Engineering, http://www.scirp.org/journal/jbise 2019, Vol. 12, (No. 1), pp: 40-52 Breath Analysis for Detecting Diseases on Respiratory, Metabolic and Digestive System Lu Kou1, David Zhang1,2*, Jane You1, Yingbin Jiang2 1Biometrics Research Center, Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China; 2Department of Computer Science, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China Correspondence to: David Zhang, Keywords: E-Nose, Chemical Sensors, Breath Analysis Received: November 26, 2018 Accepted: January 26, 2019 Published: January 29, 2019 Copyright © 2019 by authors and Scientific Research Publishing Inc. This work is licensed under the Creative Commons Attribution International License (CC BY 4.0). http://creativecommons.org/licenses/by/4.0/ Open Access ABSTRACT Recently, biological technology and computer science are of great importance in medical applications. Since one’s breath biomarkers have been proved to be related with diseases, it is possible to detect diseases by analysis of breath samples captured by e-noses. In this pa- per, a novel medical e-nose system specific to disease diagnosis was used to collect a large-scale breath dataset. Methods for signal processing, feature extracting as well as fea- ture & sensor selection were discussed for detecting diseases on respiratory, metabolic and digestive system. Sequential forward selection is used to select the best combination of sen- sors and features. The experimental results showed that the proposed system was able to well distinguish healthy samples and samples with different diseases. The results also showed the most significant sensors and features for different tasks, which meets the rela- tionship between diseases and breath biomarkers. By selecting best combination of different sensors and features for different tasks, the e-nose system is shown to be helpful and effec- tive for diseases diagnosis on respiratory, metabolic and digestive system. 1. INTRODUCTION Traditional diagnosis methods include blood, urine tests and some other methods. Nowadays, bio- logical technology and computer science are playing their roles in medical applications. Technic develop- ments in bioimaging [1], biochips [2] and biosensors [3] have brought new aids in disease diagnosis. Breath analysis is a way to detect some diseases by the examination of certain compounds in human breath, which is largely composed of oxygen, carbon dioxide, water vapor and nitric oxide, as well as less than 100 ppm (parts per million) of mixture with over 500 kinds of components. The components include carbon monoxide, methane, hydrogen, acetone and numerous volatile organize compounds (VOCs) [4, 5]. https://doi.org/10.4236/jbise.2019.121004 40 J. Biomedical Science and Engineering Table 1 summarizes the concentrations of typical compositions from human breath [6]. A breathing process includes three stages. The first stage is the exchange of gases between the outside air and the alveoli and between the alveoli and the blood in pulmonary capillary. The second is the ex- change between oxygen and carbon dioxide in blood during gas transportation in the blood. The third is the exchange of gases between blood and tissue cells. During this process, endogenous molecules produced by metabolic processes are separated from blood and enter into the alveolar air via the alveolar pulmonary membrane [6-8] and thus into the exhaled breath. Variation in the concentration of these molecules can suggest various diseases or at least changes in metabolism [9]. For instance, nitric oxide in breath can be measured as an indicator of asthma or other conditions characterized by airway inflammation [10]. In- creased pentane and carbon disulfide have been observed in the breath of patients with schizophrenia [11]. Breath concentration of volatile organic compounds (VOCs) such as cyclododecatriene, benzoic acid, and benzene is much higher in lung cancer patients than in control groups [12]. Acetone has been found to be more abundant in the breath of diabetics [13, 14], and breath ammonia is significantly higher in patients with renal diseases [15]. These molecules are considered as biomarkers of the presence of diseases and clinical conditions. Much can be learnt from them about the overall state of an individual’s metabolism or physical condition. Compared with these methods, breath analysis has many advantages [16]. Firstly, breath analysis is a non-invasive method, and it causes least harm to both the subjects and the personnel who collect the sam- ples. Secondly, its result can be obtained immediately. Thirdly, the sample collection is quite easy for a subject, since the only requirement to collect a breath sample is that the subject must be breathing. There- fore, increasing interest has been expressed about the applications of breath analysis in medicine and clin- ical pathology [17, 18]. However, most of the existing trials [19] on breath diagnosis only focus on very limited kinds of diseases. The reason may be complicated. Lack of specific breath analysis system and me- thod, as well as a large enough dataset will all block the process of research. Also, some of the diseases may not be so related to the breath system, which will not give a satisfactory result. Basing on the process of gas exchange in breath, we can see that diseases of respiratory system and metabolic system will strongly affect one’s exhaled breath. On the other hand, since the respiratory passage is connected to digestive system, it may be possible to detect diseases of digestive system by breath analysis. We thus collected a breath analy- sis dataset with both healthy samples and samples with different kinds of diseases of respiratory, metabolic and digestive system by a specific e-nose system. Experiments were organized on the collected dataset to discover a proper method of breath analysis for disease diagnosis. 2. LITERATURE REVIEW 2.1. Breath Biomarker and Diseases Nowadays, the concentration of some biomarkers in breath has been proven to be related with certain diseases. For example, lung diseases may alter volatile organic compounds (VOCs) in breath because both Mycobacteria and oxidative stress resulted from Mycobacterial infection generate distinctive VOCs. And digestive system diseases will reflect in hydrogen of ones’ exhaled breath because sugar could not be fully digested and would be decomposed or fermented and produce more hydrogen. By selecting proper sensors that can respond to the components, it is possible to analyze a person’s breath odor and thus his or her health state. A few examples will further prove these points. The level of nitric oxide can be used as a di- agnostic for asthma [20]. Patients with renal disease have higher concentrations of ammonia [21]. The concentration of VOCs, such as cyclododecatriene, benzoic acid, and benzene is much higher in lung can- cer patients [22]. Table 2 lists the relationship between biomarkers and some typical diseases. 2.2. Breath Analysis with E-Nose Currently, the measurement of exhaled breath is usually performed by two common gas analysis ap- paratuses, gas chromatography (GC) [26] or electronic nose (e-nose) [27]. GC can separate and identify molecules that are responsible for typical odors occurring in specific diseases, which is very accurate for https://doi.org/10.4236/jbise.2019.121004 41 J. Biomedical Science and Engineering Table 1. Typical compositions of human breath. Concentration Molecules percentage oxygen, water, carbon dioxide acetone, carbon monoxide, methane, parts-per-million hydrogen, isoprene, benzenemethanol formaldehyde, acetaldehyde, 1-pentane, ethane, ethylene, other hydrocarbons, nitric oxide, carbon disulfide, methanol, parts-per-billion carbonyl sulfide, methanethiol, ammonia, methylamine, dimethyl sulfide, benzene, naphthalene, benzothiazole, ethane, acetic aide Table 2. Breath biomarkers and related diseases. Diseases Breath Biomarkers diabetes [6] acetone kidney disease [23] ammonia benzene,1,1-oxybis-, 1,1-biphenyl,2, lung disease [12] 2-diethyl, furan,2,5-dimethyl-, etc. Respiratory disease [24] pentane, nitric oxide, carbon monoxide digestive system disease [25] hydrogen disease identification. But this kind of apparatus is expensive and not portable. Its sampling and assaying processes are complicated and time consuming (about one hour for one sample), and its results require expert’s interpretation [28]. Therefore, it is hard to use such apparatus as a domestic or clinical tool. Electronic noses, or e-noses, are devices that “smell” or detect odor. An e-nose consists of a mechan- ism for chemical detection, such as an array of electronic sensors, and a mechanism for processing. Using e-nose is a less expensive and more portable way for breath analysis. Recently, e-nose has gradually been used in medicine for the diagnosis of renal disease [29], diabetes [30], lung cancer [31], and asthma [32]. Though all of these methods work satisfactorily in breath analysis, their results could possibly be im- proved. That is because, commercial e-noses, with their marketing concerns, have to provide versatility in applications, such as coffee, wine, and fragrances identification. The versatility, however, limits their per- formance in disease detection since their sensor selection has to match broad applications. The idea of e-nose is inspired by the mechanisms of human olfaction. In general, basic elements of an e-nose system include an “odor” sensor array, a data preprocessor,
Details
-
File Typepdf
-
Upload Time-
-
Content LanguagesEnglish
-
Upload UserAnonymous/Not logged-in
-
File Pages13 Page
-
File Size-